© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 885
    Prev
    Next
    INDEX
    Explanations

    cortical, insulin, diabetes, blood, frailty

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects motivational, health-oriented advice or “pep-talk” style sentences (e.g. encouraging you to stick with a routine for better results).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     statement
    0.58
     company
    0.57
     Washington
    0.57
     ventures
    0.57
     own
    0.57
     oeuvre
    0.57
     products
    0.56
    .
    0.55
     number
    0.55
     product
    0.54
    POSITIVE LOGITS
    血糖
    0.82
    糖尿病
    0.77
    Diabetes
    0.73
     రక్త
    0.68
     मधुमेह
    0.67
     Insulin
    0.66
     혈
    0.65
     Diabetes
    0.64
    diabetes
    0.64
     Hesap
    0.64
    Activations Density 0.024%

    No Known Activations